443715 (1) [Avatar] Offline
#1
Hi!

It didn't become clear to me why you divide the loss + regularization by 2*x_train.size

Is this just an arbitrary value?

cost = tf.div(tf.add(tf.reduce_sum(tf.square(Y-y_model)),
tf.mul(reg_lambda, tf.reduce_sum(tf.square(w)))),
2*x_train.size)


Thank you very much.